Files
kserve/test/benchmark/tf_flowers_hpa.yaml
2022-06-03 14:49:43 -04:00

21 lines
537 B
YAML

apiVersion: "serving.kserve.io/v1alpha2"
kind: "InferenceService"
metadata:
name: "flowers-sample-hpa"
annotations:
autoscaling.knative.dev/class: hpa.autoscaling.knative.dev
autoscaling.knative.dev/metric: cpu
autoscaling.knative.dev/target: "60"
spec:
default:
predictor:
tensorflow:
storageUri: "gs://kfserving-examples/models/tensorflow/flowers"
resources:
requests:
cpu: "4"
memory: "2Gi"
limits:
cpu: "4"
memory: "2Gi"